mlsanityData to 14 Oct 2026

Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization

arXiv 2603.11600 ↗First posted 12 Mar 2026cs.LG cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms -- assumed known a priori -- directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization objective to enforce energy-efficient control. A complete theoretical foundation is established: functional independence of shaping and regularization, energy-based gradient enrichment under positive-definite Hessian conditions, convergence guarantees under function approximation, and approximate potential error bounds. Across four continuous control benchmarks and four baseline algorithms, H-EARS achieves consistent gains in convergence speed, policy stability, and final performance. High-fidelity vehicle simulations validate applicability in safety-critical settings under extreme road conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 32 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

17 of 32 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  7. 2017Deep Reinforcement Learning that Matterscited by 754
  8. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  9. 2019Hamiltonian Neural Networkscited by 712
  10. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
  11. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 436
  12. 2020Lagrangian Neural Networkscited by 398
5 more
  1. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  2. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
  3. 2017Optimization-Based Autonomous Racing of 1:43 Scale RC Carscited by 50
  4. 2016Learning Model Predictive Control for iterative tasks. A Data-Driven Control Frameworkcited by 39
  5. 2023Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control
  2. 2026Optimal Reward Shaping: Autonomous Car Parking Case Study
  3. 2026Sufficiency of Zeroth-Order Reward Shaping for Policy Gradient in Stabilization Control
  4. 2025Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
  5. 2025Sequence Aware SAC Control for Engine Fuel Consumption Optimization in Electrified Powertrain
  6. 2024Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
  7. 2026PIRS: Physics-Informed Reward Shaping for SAC-Based Building Energy Management
  8. 2026Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management